Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Thursday 10 September

Computer Vision

Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators

Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger et al. (+3 more)

High-resolution digital surface models (DSMs) play an important role in urban analysis, 3D building reconstruction, and infrastructure monitoring, yet their availability remains limited due to the high cost and complexity of data acquisition. In contrast, coarse DSMs from commercial satellite missions are widely accessible, and high-resolution optical imagery is increasingly available from aerial and satellite platforms. We address the resulting mismatch in spatial resolution and propose a DSM superresolution approach that enhances 5 m DSMs to 0.5 m resolution, using guidance from high-resolution spectral images. Our method employs denoising diffusion to transfer information that is visible only in the image, like crisp outlines and detailed roof structures, into the elevation maps. In this way, surface details are reconstructed more accurately than with conventional interpolation or filtering techniques. Experiments on several cities in Central Europe demonstrate that the proposed approach produces high-quality DSMs with improved structural detail and accurate surface geometry. Our results highlight the potential of guided super-resolution with foundational image priors as a means of reconstructing high-resolution surface models.
Read the full abstract

All authors Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger, Daniel Panangian, Ksenia Bittner, Konrad Schindler

Machine Learning

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

Yifan Yang, Zhaoyan Wang, Zheng Gao et al. (+2 more)

Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement. CoRA-Rank aggregates capacity and structure-at-initialization proxies through an equal-weight log-rank consensus and a target-free consensus gate. CoRA-Refine samples anchors across this prior, extrapolates their early validation curves, and propagates a learned residual correction with an ExtraTrees model. The refinement uses approximately 1% of the cost of fully training the candidate set. Fully trained architecture-accuracy labels are not used to fit the ranker. One configuration is used across spaces, with space-specific architecture encodings. Across NAS-Bench-201, NAS-Bench-101, TransNAS-Bench-101, and NATS-SSS, CoRA-Refine achieves mean Spearman correlations of 0.946, 0.715, 0.786, and 0.894, respectively. Its worst-space correlation of 0.715 is the highest among the compared methods. On NAS-Bench-201/CIFAR-100, its selected architecture reaches 73.32% accuracy, near the reported ground-truth best of 73.37%. On the pure size space, refinement recovers the static prior's shortfall relative to parameter count, while remaining tied with the strongest capacity proxies within noise. The resulting framework combines cross-space ranking robustness with low-cost architecture selection.
Read the full abstract

All authors Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang

Cryptography and Security

From Specs to Apps: Verifying and Monitoring Models of Signal and WhatsApp

Moustafa Said, Aurora Naska, Kevin Morio et al. (+1 more)

The Signal protocol is a prominent messaging protocol that secures communication for billions of users. It powers WhatsApp, the most widely used messaging application worldwide, and the Signal app, popular among privacy-conscious users. Extensive research in the computational and Dolev-Yao settings provides strong formal security guarantees for the protocol itself. However, a gap remains between the guarantees of the protocol specification and the implementation's actual behavior at runtime. In this work, we bridge this gap by applying SpecMon, a recently proposed runtime monitor, to check whether observed executions conform to formal protocol models. To this end, we instrument two applications (WhatsApp Web and Signal Desktop) to capture their interactions with the network and the cryptographic components. Using this instrumentation, we develop two multiset-rewrite models that are compatible with Tamarin, thus enabling verification. We derive the first model of WhatsApp Web's implementation of the Signal protocol and the most detailed model to date of Signal's original protocol. Monitoring establishes that observed executions conform to these models, relative to the trusted event extraction and the symbolic abstraction. For the core components of the Signal protocol, we verify authentication and secrecy properties. Finally, monitoring reveals previously undocumented differences between the original libsignal library and WhatsApp's fork. We evaluate our methodology and demonstrate its reproducibility. Developing the WhatsApp Web model, instrumenting the app, adding fuzzing, and running the experiments took three person-weeks. We also demonstrate efficient monitoring of real-world applications and detection of deliberately injected security faults, with low overhead in our measured setting.
Read the full abstract

All authors Moustafa Said, Aurora Naska, Kevin Morio, Robert Künnemann

Computation and Language

Domain-Specific Hallucination Detection in Large Language Models

Varun Teja Chundru and Debasmita Biswas

Large language models generate fluent text that can contain unfaithful claims – a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection. Evaluated on the HaluEval benchmark, our pipeline achieves F1=0.915 and AUROC=0.977 on general-domain tasks, with per-task F1 scores of 0.97 (QA), 0.96 (Summarization), and 0.82 (Dialogue). MC Dropout inference further improves accuracy to 93.2%. A context ablation study confirms the model performs genuine entailment reasoning rather than exploiting surface patterns, with summarization F1 dropping 24% when knowledge context is removed. Learning curve analysis reveals that 25% of training data captures 77% of full-data performance. Beyond detection, we apply Direct Preference Optimization (DPO) to a Qwen2.5-0.5B generator, reducing its hallucination rate from 85.5% to 37.7% (55.9% relative reduction) as measured by our detector. Cross-domain evaluation on the SciFact biomedical benchmark shows that general-domain training transfers poorly (F1=0.52), motivating domain-specific fine-tuning. PubMedBERT fine-tuned on SciFact achieves F1=0.63 and AUROC=0.81, demonstrating that domain-matched pre-training is the strongest adaptation strategy. Code and models are available at https://github.com/varunteja99/hallucination-detection-nlp
Read the full abstract

Artificial Intelligence · Cross-listed from q-bio.QM

Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens

Carl Edwards, Edward De Brouwer, Xiner Li et al. (+5 more)

Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must instead be prioritized over multiple experimental rounds. Despite the importance of this problem, existing benchmarks for adaptive hit discovery remain limited in scale and diversity. Here, we introduce AssayBench-Loop, a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories. Beyond enabling systematic evaluation, its scale makes it possible to learn acquisition strategies across historical experiments. Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback, with LLM-derived biological priors through an adaptive handoff. In this view, completed experiments become training data for learning how accumulated evidence should guide what to test next, while LLMs provide prior biological knowledge to seed the search. We further introduce AssayLLM, showing that the same principle can be extended directly to an LLM through task-specific post-training. On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs, and AssayFormer alone. Performance improves with increasing historical training data and transfers to phenotype categories excluded from training. These results demonstrate the value of learning acquisition policies across historical experiments and combining them with broad biological priors for efficient adaptive hit discovery.
Read the full abstract

All authors Carl Edwards, Edward De Brouwer, Xiner Li, Namkyeong Lee, Ehsan Hajiramezanali, Anne Biton, Sara Mostafavi, Gabriele Scalia

Artificial Intelligence

On the Regularization Landscape for the Linear Recommendation Models

Dong Li, Zhenming Liu, Ruoming Jin et al. (+4 more)

Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders on several standard recommendation benchmarks. While these algorithms were built on different DL techniques (e.g., dropouts, autoencoder), they have similar performance and even similar cost functions. This paper studies whether the models' comparable performance are sheer coincidence, or they can be unified under a single framework. We find that all linear performance leaders effectively add only a nuclear-norm based regularizer, or a Frobenius-norm based regularizer. The former ones possess a (surprising) rigid structure that limits the models' predictive power but their solutions are low rank and have closed form. The latter ones are more expressive and more efficient for recommendation but their solutions are either full-rank or require executing hard-to-tune numeric procedures such as ADMM. Along this line of finding, we further propose two low-rank, closed-form solutions, derived from carefully generalizing Frobenius-norm based regularizers. The new solutions get the best of both nuclear-norm and Frobenius-norm world.
Read the full abstract

All authors Dong Li, Zhenming Liu, Ruoming Jin, Hao Zhou, Zhi Liu, Jing Gao, Bin Ren

Robotics

UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition Modeling

Wei Li, Rui Shao, Jie He et al. (+3 more)

Recent advances in Vision-Language-Action (VLA) models have improved robotic manipulation, yet observation-to-action learning remains limited by a fundamental transition realizability gap, manifested in three tightly coupled problems: (i) Transition ambiguity. Visually similar current observations may correspond to different manipulation phases and imply different subsequent transitions. (ii) Prediction–execution mismatch. A visually plausible predicted future observation does not necessarily correspond to a physically realizable transition. (iii) Experience–realization mismatch. A historically executable action pattern may not necessarily realize the intended transition in the current scene and therefore requires context-aware adaptation. Accordingly, we propose UniMPA, a Unified Memory-Prediction-Action model that addresses these problems through a shared action-grounded transition interface. (i) UniMPA introduces Persistent-Selective Future Prediction to resolve transition ambiguity by modeling the intended future state evolution. A persistent latent stream continuously tracks task-level progress, while a transition-critical pixel stream selectively resolves fine-grained interaction changes through memory-grounded prediction. (ii) To assess the physical executability of the anticipated transition, the predicted transition queries a temporal Visual-Action Memory Bank. The bank retrieves historically realized visual-action experience, grounding future prediction in executable evidence. (iii) To adapt executable experience to the current scene, an Action-Visual Memory Bank retrieves visually grounded action prototypes from historical action evolution. Prototype-Biased Flow then shifts the flow source toward a historically supported action manifold for context-aware refinement.
Read the full abstract

All authors Wei Li, Rui Shao, Jie He, Lingsen Zhang, Ziwei Liu, Liqiang Nie

Machine Learning

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Yi Duan, Ying Liu, Zirui Tang et al. (+32 more)

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.
Read the full abstract

All authors Yi Duan, Ying Liu, Zirui Tang, Haodong Chen, Jun Zhou, Yumou Liu, Bangrui Xu, Yukai Wu, Sidi Chen, Yuhan Zhou, Haoyu Wang, Xiaoyou Yu, Shaokun Han, Xuzhou Zhu, Le Zhou, Bolin Lu, Wei Zhou, Jiachen Liu, Nuozhou Fang, Jiaxin Tian, Ruoyu Chen, Yuxuan Li, Kai Zuo, Kaiyan Zhang, Qianyu Yang, Zijie Wang, Jiantao Qiu, Conghui He, Guoliang Li, Bowen Zhou, Zhiyuan Liu, Zhoufutu Wen, Jihua Kang, Xuanhe Zhou, Fan Wu

Machine Learning · Cross-listed from stat.ML

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang et al. (+9 more)

Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods.
Read the full abstract

All authors Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang, Evie L. Shen, Joleen Vansomphone, Yuna Li, Kerry Zhou, Zitian Qu, Suning Zhao, Xiangning Deng, Hua Zhou, Jin J. Zhou

Robotics

Learning Agent-based Model Predictive Control for Holistic Vehicle Performance

Jiaming Zhong, Reza Valiollahi Mehrizi, Mohammad Pirani et al. (+4 more)

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance. However, its optimality highly depends on the prediction accuracy that requires all agents or their contributions to be known, which is too idealistic for actual implementation. This research proposes a novel practical hybrid control scheme - learning agent-based MPC (LAMPC), combining the model-based AMPC approach and data-based learning methods to improve the holistic vehicle performance for multi-agent systems. The Gaussian process regression (GPR) enhanced by an online data management strategy serves as the learning core to predict unknown contributions. A novel multi-step prediction mechanism leverages the GPR learning potential along the horizon. The predicted mean, representing the learned unknown contributions, completes the system model in the MPC for more accurate control. Meanwhile, a stochastic framework is formulated to guarantee control safety and feasibility using soft chance constraints based on the prediction variance. Both simulations and experiments show that, with the learning capability, LAMPC outperforms the traditional AMPC. LAMPC can achieve higher tracking performance in well-learned scenarios and always guarantee constraint satisfaction even in less-learned scenarios. Moreover, the proposed hybrid control scheme is efficient for real-time implementation and is flexible to any control agent topology.
Read the full abstract

All authors Jiaming Zhong, Reza Valiollahi Mehrizi, Mohammad Pirani, Chao Yu, Alireza Kasaiezadeh, Yash Vardhan Pant, Amir Khajepour

Computation and Language

Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model

Lisa Bylinina

A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word learning, meaning by ostension, for a small masked language model (DeBERTa) trained on 10M words: before training, visually grounded tokens receive embeddings derived from the image regions they label; other tokens start random. Visual initialization leaves a measurable imprint that lasts until the end of training. At the same time, the effect remains invisible under most BabyLM benchmarks, which probe abstract grammatical knowledge: visual initialization does not affect performance there. The only zero-shot exception is object-property knowledge (COMPS), where seeding helps in every configuration. To follow up on this result, I build a corpus-tailored version of the Visual-Property Swap benchmark, which tests color, material, size, and shape knowledge, with per-item training frequency and seeded status. Here, vision-seeded models have a persistent, seed-replicated advantage. Function words and abstract vocabulary also receive strong visual seeds and retain them throughout training, and the training objective draws on them: held-out mask-prediction loss falls for these words in every seed. However, no benchmark I run registers this. What evaluation would pick this up remains an open question.
Read the full abstract

Machine Learning

AdamX: Cosine similarity meets gradient descent

Francisco Caldas, Ruben Belo and Cláudia Soares

We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-agnostic, and straightforward to integrate into existing training pipelines. We further introduce a variance rectification scheme that promotes smoother optimization during the early stages of training. Overall, we provide empirical evidence that AdamX achieves competitive convergence rates across a range of benchmark datasets and architectures. Performance is evaluated in terms of the number of epochs required to reach predefined performance thresholds under a fixed hyperparameter budget. Code and Experiments available at: https://github.com/FranciscoCaldas/adamX.
Read the full abstract

Computation and Language

Epistemic orientation predicts legislative effectiveness among members of the US Congress

Segun Aroyehun, Stephan Lewandowsky and David Garcia

Truth and evidence-based communication provide important foundations for democratic governance, accountability, and collective decision-making. Prior work shows that evidence-oriented language in US congressional floor speeches has declined since the mid-1970s, alongside broader changes in legislative productivity and polarization. This study shifts the analysis from congressional sessions to individual members of Congress to examine whether epistemic orientation varies systematically across legislators and whether it relates to political behavior and legislative effectiveness. Using the Evidence-Minus-Intuition (EMI) score, we measure the relative prevalence of evidence-oriented versus intuition-oriented language in congressional floor speeches and Twitter posts. We link these measures to legislator-level data on ideology, institutional position, communication context, and Legislative Effectiveness Score (LES). The results show that more ideologically extreme members use less evidence-oriented language on the congressional floor. EMI also exhibits cross-platform consistency with members who use more evidence-oriented language in floor speeches also being more evidence-oriented on Twitter, although EMI is lower on Twitter overall. Finally, EMI in congressional speeches is positively associated with individual legislative effectiveness, even after accounting for ideology and extensive political, institutional, demographic, topical, and communication volume controls. These findings suggest that evidence-oriented language is not only an aggregate feature of congressional discourse but also a meaningful attribute of individual-level legislative communication and effectiveness.
Read the full abstract

Artificial Intelligence · Cross-listed from eess.AS

RetroThinker: Enabling Retrospective Thinking in Speech LLMs

Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed et al. (+1 more)

Speech large language models (SpeechLLMs) offer reduced latency and retain paralinguistic nuances that are typically lost in cascaded automatic speech recognition (ASR) and text-based LM architectures. However, they continue to lag behind text-only LLMs on complex reasoning tasks, while real-time spoken interaction imposes strict latency constraints. Although prior works employ Chain-of-Thought (CoT) and concurrent reasoning to enhance reasoning capabilities without inducing prohibitive delays, an inherent accuracy-latency trade-off persists. In this paper, we investigate whether a streaming SpeechLLM can dynamically revise its reasoning traces on the fly. We introduce RetroThinker, a multi-stage post-training framework that equips the Moshi model to self-verify and forward-correct CoT steps during inference. RetroThinker combines supervised fine-tuning (SFT) on curated retrospective thinking data with length-based direct preference optimization (DPO) to optimize retrospective during early reasoning (i.e., reasoning concurrently while the user speaks). Evaluated on the GSM8K benchmark, RetroThinker significantly improves the accuracy-latency trade-off over non-retrospective baselines, achieving an 11% absolute accuracy gain at a comparable latency.
Read the full abstract

All authors Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed, David Harwath

Game Theory

Truncated Noisy Best-Response Algorithms: Toward Game Theoretic Learning with Safety Guarantees

Vartika Singh and Philip N. Brown

We consider a game theoretic approach to solve multi-agent coordination problems with submodular maximization objectives. It is known for such problems that the Nash equilibria for the corresponding game are always within 50% of the optimal, but that the equilibria which achieve this worst-case bound are not stable. To exploit this instability, we propose a family of algorithms which we call Truncated Noisy Best-Response (TNBR) Algorithms. These algorithms are flexibly characterized by agents asynchronously and stochastically selecting actions from a neighbourhood of their best response payoffs. We compute bounds on the recurrent classes of TNBR algorithms' associated Markov chains. Our bounds fall into two categories: first, "Performance" bounds ensure that TNBR algorithms always have a high-value recurrent state; second, "Safety" bounds ensure that TNBR algorithms never have arbitrarily-bad recurrent states. Furthermore, these two types of bounds are linked by a waterbed-like effect: every game with a poor Safety guarantee necessarily has a favorable Performance guarantee.
Read the full abstract

Artificial Intelligence

Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models

Rodion Krjutškov, Eduard Barbu, Nikos Sakkas et al. (+1 more)

Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret. Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require substantial technical expertise and provide limited flexibility for dynamic, context-aware inquiry. Conversational XAI systems offer a promising alternative; however, previous approaches, such as TalkToModel, were constrained by rigid custom grammars and achieved only 76.8% intent-parsing accuracy. This paper introduces the Explainability Assistant, an open-source conversational XAI system that leverages the function-calling capabilities of modern Large Language Models (LLMs) to overcome these limitations. The system achieves 94% intent-parsing accuracy, supports flexible natural language interaction, and adapts to different ML problem types without task-specific fine-tuning. We present the system's architecture and report results from a comparative evaluation conducted with energy domain specialists, contrasting the Explainability Assistant with a traditional XAI dashboard. The evaluation suggests improved usability and consistent task accuracy, with all experts unanimously preferring the conversational interface for practical use.
Read the full abstract

All authors Rodion Krjutškov, Eduard Barbu, Nikos Sakkas, Sofia Yfanti

Artificial Intelligence

From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge

Wenkang Wei, Yuan Fang, Renhe Jiang et al. (+2 more)

How does a language model's dependence on query-routing information and target knowledge change as it answers a question? We study this question through layerwise interventions on the hidden state at the end of the question. Across Qwen, Llama, and Gemma, we compare country-continent questions with noun, adjective, and code answers while keeping several fitted measurements distinct. A pair-conditioned request direction describes which country is queried in natural single-country questions; a global request direction describes first- versus second-country requests in paired questions; separate selection candidates test control among contents already available in the hidden state. A diagnostic reanalysis of frozen Qwen natural-question states shows that the pair-conditioned direction grows stronger before interventions on it begin to alter later fitted knowledge, with this causal window opening while answer-supporting content is still forming. The paired three-model trajectories are not uniform: Gemma shows a partially overlapping mid-layer routing-content profile, whereas Llama has no sustained routing-effect window under the same gates. In the paired protocol, dependence on the global request direction decreases from fixed earlier to later layer sets while dependence on fitted content persists. A matched Qwen comparison shows that the pair-conditioned direction retains a late effect, so this operational handoff concerns the global fitted direction rather than all request information. These results separate early readability, natural strength, causal steering, and later content dependence.
Read the full abstract

All authors Wenkang Wei, Yuan Fang, Renhe Jiang, Hong Cheng, Xingtong Yu

Computational Complexity · Cross-listed from quant-ph

PureSuperQMA(exp) = BellPureSymQMA(poly) = QMA via Dimension-Free Bosonic Argmax

William Gay, Fernando Granha Jeronimo, Lenny Liu et al. (+3 more)

Pure-state consistency problems naturally lead to quantum proof systems in which a single pure witness must satisfy many acceptance constraints. The corresponding class $\mathsf{PureSuperQMA}$ was previously known to lie between $\mathsf{QMA}$ and $\mathsf{QMA}(2)$, and Kamminga and Rudolph (ITCS'26) conjectured that both containments are strict. In this paper, we prove the following surprising complexity collapses $$ \mathsf{QMA} = \mathsf{PureSuperQMA} = \mathsf{PureSuperQMA}(\text{exp}) = \mathsf{BellPureSymQMA}(\text{poly}) $$ Here $\mathsf{PureSuperQMA}(\text{exp})$ allows exponentially many checks which are uniformly indexed and efficiently generated, while requiring an inverse-polynomial violation margin and an inverse-polynomial fraction of violated checks for the NO cases. $\mathsf{BellPureSymQMA}(\text{poly})$ is a related model that requires the prover to give the verifier polynomially many copies of a pure state, which the verifier measures separately with logarithmic output length for each local measurement, before processing the outcomes jointly. The main technical ingredient is a dimension-free stability bound for symmetric tensor states. Our simulations use polynomially many witness registers and combine a random-pair SWAP test with a permutation-invariant lift of the original verification procedure. The key step is to show that, on the symmetric subspace, the extremal verification value is close to that of some tensor-power witness with dimension-independent error. Applying this argument to the two verification models yields both simulations. As a consequence, exact $k$-local pure-state consistency is $\mathsf{QMA}$-complete for every fixed $k\ge2$, and so are the corresponding exact bosonic and fermionic pure $N$-representability problems.
Read the full abstract

All authors William Gay, Fernando Granha Jeronimo, Lenny Liu, Itai Leigh, Pei Wu, Haochen Xu

Cryptography and Security

BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense

Simona Boboila, Xavier Cadet, Edward Koh et al. (+4 more)

Cyber attacks are increasingly automated, narrowing the time available for human analysts to detect, reason about, and respond to intrusions. Large language models (LLMs) offer a promising foundation for autonomous cyber defense because they can correlate heterogeneous evidence and reason about previously unseen threats. However, directly applying LLMs to operational security telemetry is impractical: raw logs arrive faster than current models can process them, individual events are often ambiguous, and unconstrained LLM actions can introduce significant operational risk. We present BlueSTAR, a tiered agentic architecture for autonomous cyber defense in enterprise IT/OT networks. BlueSTAR first transforms high-volume security telemetry into compact indicators of compromise. We further introduce a resilience metric that jointly captures attacker reach, impact on mission-critical assets, and disruption caused by defensive actions. We evaluate BlueSTAR on two live enterprise IT/OT cyber ranges using seven attack chains based on real-world intrusion techniques. Across attack chains, BlueSTAR retains the fast containment of deterministic response for known threats while successfully defending against attacks requiring contextual and cross-cycle reasoning, including credential theft, repeated compromise, concurrent attackers, and attacks against physical processes.
Read the full abstract

All authors Simona Boboila, Xavier Cadet, Edward Koh, Daniel Balasubramanian, Dirk Van Bruggen, Peter Chin, Alina Oprea

Computation and Language

IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing

Pruthwik Mishra, Rudra Trivedi, Avi Patel et al. (+2 more)

Language identification in code-mixed text, largely observed in social media, is highly essential when users frequently switch between multiple languages within a single utterance. Accurately identifying the languages of code-mixed tokens becomes an urgent necessity. Traditional language identification models, designed for monolingual text, are not well suited for token-level language identification in code-mixed settings. We formulate the task as a sequence labeling problem and fine-tune contextual transformer-based models MuRIL and XLM-RoBERTa best suited for Indian languages. We evaluate these systems on three different data configurations (Hindi, Gujarati, and Bengali) to predict language labels for individual tokens. We release a benchmark for language identification in code-mixed tokens with manually annotated test sets. We propose two approaches of code-mixed generation using parallel sentences of three languages. The trained models demonstrate the effectiveness of contextual embeddings for token-level language identification in multilingual social media text. For reproducibility and to facilitate future research, we publicly release our fine-tuned models.
Read the full abstract

All authors Pruthwik Mishra, Rudra Trivedi, Avi Patel, Ashok Urlana, Shrikant Malviya

Networking

From Open RAN to Open Spectrum: A Programmable, Intelligent Architecture for Multi-Service Spectrum Coexistence

Michele Polese, Minh Dat Nguyen, Paolo Testolina et al. (+1 more)

Considering sharing or coexistence from the perspective of spectrum alone fails to recognize that any spectrum-enabled service also requires (i) radio and processing infrastructure and (ii) a protocol stack, including waveforms and signal processing pipelines. The efficiency of spectrum coexistence frameworks such as Citizen Broadband Radio Service (CBRS) is thus limited to optimizing resource allocation across a single dimension. How to address this limitation, however, remains an open challenge, especially considering the diversity of requirements and operational modes across spectrum services (e.g., sensing, communications, navigation, or positioning). This article introduces Open Spectrum, an architecture that brings softwarization, programmability, and open interfaces to heterogeneous spectrum services, extending the open Radio Access Network (RAN) principles beyond wireless networking. We propose to combine spectrum, services, and infrastructure in a common pool. Its resources are shared and orchestrated by a Spectrum Intelligent Controller (SIC), with plug-and-play spectrum applications, i.e., Spectrum Applications (sApps), and data-driven Radio-Frequency Interference (RFI) modeling using Digital Twins (DTs). We describe the Open Spectrum architecture, shared infrastructure pool, and operational workflows for tenant onboarding and incentives, conflict resolution, and service sharing across sensing, radionavigation, radiolocation, and cellular systems. System-level simulations using the BostonTwin urban DT and Sionna ray tracing show that there exist performance-driven incentives in sharing infrastructure and sharing across multiple services, enabling increased access to spectrum and improvement in median Signal to Interference plus Noise Ratio (SINR) of up to 12 dB.
Read the full abstract

All authors Michele Polese, Minh Dat Nguyen, Paolo Testolina, Tommaso Melodia

Machine Learning

Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport

Luyi Jia, Boyan Zhang, Yilun Liu et al. (+1 more)

Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coefficient paths, motivated by optimal transport, helps explain strong baselines but remains model-agnostic and ignores prediction error. Here we introduce a model-aware schedule construction based on fiberwise optimal transport. At a fixed time and state on the probability path, compatible signal/noise decompositions form an affine fiber. We define a fiberwise prediction risk by averaging optimal-transport costs between the true and predictor-induced decompositions within these fibers. On a fixed coefficient curve, combining this risk with coefficient-path kinetic action yields a closed-form optimal time allocation. This construction extends to general linear prediction targets, and the risk profile can be estimated from an early baseline checkpoint. We evaluate DDPMs and flow matching across prediction targets, training configurations, risk-estimation checkpoints, datasets, and architectures. Our model-aware schedules consistently outperform strong baselines, including a 38.6% relative FID reduction for flow matching on CIFAR-10 at 16 function evaluations. Each model-agnostic kinetic baseline determines its own kinetic reference coordinate. In these coordinates, fiberwise-risk profiles from independently trained models in different settings align closely after normalization to unit area. The resulting schedule deformations used in training also align, suggesting empirical universality across the evaluated models and settings. Pretrained-checkpoint diagnostics extend this normalized-risk agreement to larger conditional latent diffusion and 2-RF models. A frozen analytic allocation template retains most of the model-aware improvement without further risk estimation or model-specific fitting.
Read the full abstract

All authors Luyi Jia, Boyan Zhang, Yilun Liu, Steffen Rulands

Cryptography and Security

Atlas: Efficient Verifiable Semantic Search

Nikolay Avramov, Hidde Lycklama, Alexander Viand et al. (+1 more)

Semantic search is a core primitive of modern applications, powering recommender systems, web search, and retrieval-augmented generation for language models. The provider controls the index and query execution, leaving clients to trust that results come from the right algorithm over the intended index. A provider may truncate search to cut cost, bias results, or otherwise deviate from the specified execution undetected. Verifiability can remove this trust assumption by proving that results follow the agreed algorithm over a committed index. Realizing this efficiently is hard, as retrieval at scale relies on HNSW, a graph-based algorithm whose data-dependent traversal maps poorly onto the fixed constraint systems of zero-knowledge proofs. Prior verifiable systems therefore target regular, cluster-based indices that are easier to encode, sacrificing the recall of graph-based search. We present Atlas, a system that lets a provider prove a query was answered correctly against its committed index without revealing the index. At its core is a new zero-knowledge proof for HNSW search, built on three techniques: preprocessing that shifts all database-dependent cost offline, so per-query proving scales with the traversal rather than the database; a restructuring of HNSW into a fixed-size-state procedure that we prove returns the same result; and a timestep-tagged batching that merges the per-step arguments of the entire traversal into one. Atlas is the first to demonstrate verifiable graph-based search at scale, proving a query in under a second on the SIFT1M benchmark and in 2.0 seconds at 100 million vectors, while maintaining the recall of plaintext HNSW and revealing nothing about the index beyond the result. In a complete RAG pipeline, Atlas' proven retrieval preserves end-to-end answer quality, and reaches higher quality at lower proving cost than all prior verifiable retrieval systems.
Read the full abstract

All authors Nikolay Avramov, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

Computation and Language

Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif et al. (+2 more)

Cardiovascular screening models trained on national health surveys routinely report areas under the receiver operating characteristic curve (AUROC) near 0.89. We asked whether that accuracy reflects learning or target leakage, whether tabular foundation models change the answer, and whether the properties deployment requires survive joint examination. We benchmarked ten classifiers spanning linear, tree-ensemble, neural, glass-box, and tabular foundation classes for prevalent myocardial infarction in 442,067 respondents of the 2022 Behavioral Risk Factor Surveillance System across five feature tiers of decreasing leakage risk. Each was audited for discrimination, calibration, fairness at an explicit screening threshold, conformal coverage, explanation faithfulness, and inference cost, then applied – models and thresholds frozen – to 430,755 respondents of 2023. Removing two post-diagnostic features cost every model 0.049-0.051 AUROC, collapsing the field into a 0.0045-wide band. The glass-box explainable boosting machine was non-inferior to every alternative within a pre-specified 0.005 margin while scoring the cohort roughly 104 times faster than the strongest foundation model. One threshold detected 75.4% of women's infarctions against 89.0% of men's; editing the model's shape functions reduced the gap to 0.010. Marginal conformal prediction gave 0.86 coverage to men and 0.82 to adults over 60; Mondrian calibration repaired every stratum. Frozen models transported within 0.002 AUROC. Reported headroom in this literature is a property of the feature set, not the learner. Transparency cost nothing measurable and made fairness repair and uncertainty conditioning directly auditable. Evaluation practice, not model capacity, is the binding constraint.
Read the full abstract

All authors Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif, Samer Ellaham, Cedric Schmitz

Data Structures and Algorithms · Cross-listed from math.PR

Free-Probabilistic State Evolution and Random Matrix Discrepancy

August Y. Chen and Ahmed El Alaoui

Let $A_1,\ldots,A_n$ be independent $d \times d$ real symmetric Gaussian random matrices, and consider the linear operator $A(x) = n^{-1/2}\sum_{i=1}^n x_iA_i$, $x\in \mathbb R^n$. We construct an iterative algorithm in the Approximate Message Passing family which iterates over $A$ and its adjoint $A^*$, and establish a state evolution result which characterizes its behavior in the limit $d\to \infty, 2n/d^2 \to \alpha$ in terms of a correlated Gaussian-semicircular process in a free probability space, in the sense of strong convergence of operators. We then apply this iteration to the random matrix discrepancy problem which asks for a binary vector $x \in \{-1,+1\}^n$ such that $A(x)$ has a small operator norm. Our algorithm achieves an operator norm $2\sigma(\alpha)$, for a standard deviation $\sigma(\alpha)<1$ for all $\alpha>0$, and $\sigma(\alpha) = O(1/\sqrt{\alpha \log \alpha})$ for large $\alpha$. This resolves the algorithmic question of Kunisky-Zhang (2023) and Maillard (2025).
Read the full abstract

Computational Complexity · Cross-listed from quant-ph

Oracle Separations in the Fourier Hierarchy

Atul Mantri

The Fourier hierarchy $\mathrm{FH}_0\subseteq\mathrm{FH}_1\subseteq\mathrm{FH}_2\subseteq\cdots$, introduced by Shi (TCS 2005), measures a quantum computation by the number of Hadamard layers it uses. Between two layers the circuit may permute basis states and attach phases, but it may not create superposition; the layers are its only source of interference. The first level is exactly $\mathrm{BPP}$, while the second already solves Simon's problem and, through phase estimation, factors integers. Shi conjectured that every additional layer strictly increases computational power, and asked, as a first step, for oracle separations between consecutive levels. To our knowledge, the question was open at every level $k\ge2$. We prove that for every constant $k\ge2$ there is an oracle relative to which $\mathrm{FH}_k\subsetneq\mathrm{FH}_{k+1}$. The separating problem is built from Forrelation (Aaronson and Ambainis, STOC 2015): the level above solves it with a constant number of queries, whereas at level $k$ it stays hard even for circuits making exponentially many queries. This holds for both of the usual ways of giving a circuit access to an oracle, the phase oracle and the standard oracle, which writes its answer into a register. The two are not interchangeable: relative to an oracle, the standard oracle is strictly more powerful at the same number of layers. We also separate the union of all the levels from $\mathrm{BQP}$ relative to an oracle. The lower bounds rest on a structural property of the hierarchy: the number of Hadamard layers limits how adaptively a circuit can query its oracle. With a phase oracle, a circuit with $k$ layers is reproduced exactly by an algorithm making only $k-1$ rounds of parallel queries, which brings known lower bounds for such algorithms to bear. The standard oracle lets a circuit branch on earlier answers, and that case needs a separate argument.
Read the full abstract

Software Engineering

An analysis of the relationship of input metrics

Addison Crump

Input metrics evaluate the progress of testing in terms of features of inputs present in a test suite. Previous works, as early as the 1950s, established a number of such metrics, but few endeavored to compare them. This paper does so by utilizing existing methods proposed for other metric classes in partition testing literature. After defining and reviewing common input metrics, we begin with a short case study revealing that typical empirical comparison strategies are fundamentally insufficient for comparing metrics. Then, we demonstrate how one rigorously improves a standard metric by defining and implementing $k$-alt-path, a new metric which reduces redundancy while improving sensitivity over $k$-path. Each of the other common input metrics are then systematically compared before discussing the implications of our findings. With these contributions, we bring forward partition testing analysis methods that justify and form a strategy for future research in refining input metrics.
Read the full abstract

Computational Complexity

Topology inside NC$^1$

Eric Allender, Samir Datta, Arsenii Karnaukhov et al. (+3 more)

We show that ACC$^0$ is precisely what can be computed with constant-width circuits of polynomial size and polylogarithmic genus. This extends a characterization given by Hansen, showing that planar constant-width circuits also characterize ACC$^0$. Thus polylogarithmic genus provides no additional computational power in this model. We consider other generalizations of planarity, including crossing number and thickness. We show that constant-width circuits of polynomial size and thickness two already suffice to capture all of NC$^1$.
Read the full abstract

All authors Eric Allender, Samir Datta, Arsenii Karnaukhov, and Grisha Pochuev, Sambuddha Roy, Alexander Shekhovstov

Systems and Control

Acoustic-based Guidance for Automatic Docking of Holonomic AUVs

Ravi Regalo, David Cabecinhas and António Pascoal

This paper describes a system to automatically dock an AUV onto a docking station without precise knowledge of the position and orientation of the latter, in the presence of unknown ocean currents, using a fully acoustic sensing architecture. The system relies on a pair of Ultrashort Baseline sensors, one onboard the vehicle and one installed on a seabed-resident docking station, enabling operation in low-visibility environments where cameras are ineffective. Relative orientation is estimated by a nonlinear complementary filter on $SO(3)$, while an Extended Kalman Filter provides relative position, supplying pose estimates to a geometric controller on $SE(3)$ that executes the docking manoeuvre. The complete system is implemented in a dedicated software suite and validated in simulation and water trials.
Read the full abstract

Human-Computer Interaction

MotionQ: Operator-Conditioned Motion Quotients for Cross-Observation WiFi Gesture Recognition

Xiang Zhang, Huan Yan, Geying Yang et al. (+4 more)

WiFi gesture recognition is accurate in fixed deployments but often degrades when user orientation, available links, or transceiver placement changes. Unlike ordinary domain shifts, these changes alter the wireless observation operator, so the same motion is expected to produce different measurements. Existing methods nevertheless pursue domain-invariant features and largely overlook changing layouts and observation configurations. Yet changing the observation operator also changes which task-relevant motion cues are physically observable, rather than merely altering the appearance of a fixed set of cues. Under a local linearization of the WiFi forward process, we derive a common task-observability condition under which a strict common linear representation is recoverable from every geometry-induced operator while preserving the gesture task. When the condition fails, enforcing stronger alignment across additional heterogeneous source operators may discard task-relevant cues still observable under individual operators. We therefore present MotionQ, which generates an operator-conditioned two-support motion measure for each candidate geometry. A motion quotient removes only the arbitrary ordering of its unlabeled supports and is represented by permutation-invariant central moments. Rather than matching quotients across operators, single-link-retention interventions encourage each view to retain information sufficient for gesture recognition. Extensive evaluations show that MotionQ is robust to extrapolative observation operators.
Read the full abstract

All authors Xiang Zhang, Huan Yan, Geying Yang, Jianchun Liu, Tao Liu, Zhi Liu, Meng Li